---
license: apache-2.0
base_model: google/vit-large-patch16-384
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Aradam_ViTL-16-384-2e-4-batch_16_epoch_4_classes_24
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: imagefolder
      type: imagefolder
      config: default
      split: train
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.9698275862068966
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# Aradam_ViTL-16-384-2e-4-batch_16_epoch_4_classes_24

This model is a fine-tuned version of [google/vit-large-patch16-384](https://huggingface.co/google/vit-large-patch16-384) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1097
- Accuracy: 0.9698

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.1511        | 0.03  | 100  | 0.8900          | 0.7471   |
| 0.8497        | 0.07  | 200  | 0.8558          | 0.7687   |
| 0.6297        | 0.1   | 300  | 0.5995          | 0.8132   |
| 0.5735        | 0.14  | 400  | 0.4456          | 0.8649   |
| 0.307         | 0.17  | 500  | 0.4031          | 0.8851   |
| 0.3961        | 0.21  | 600  | 0.4865          | 0.8506   |
| 0.6511        | 0.24  | 700  | 0.5270          | 0.8491   |
| 0.4526        | 0.28  | 800  | 0.6105          | 0.8376   |
| 0.4071        | 0.31  | 900  | 0.3936          | 0.8937   |
| 0.2729        | 0.35  | 1000 | 0.3287          | 0.8994   |
| 0.4277        | 0.38  | 1100 | 0.5402          | 0.8621   |
| 0.2588        | 0.42  | 1200 | 0.3344          | 0.9023   |
| 0.3034        | 0.45  | 1300 | 0.3269          | 0.8922   |
| 0.2463        | 0.49  | 1400 | 0.4931          | 0.8563   |
| 0.1999        | 0.52  | 1500 | 0.3622          | 0.9037   |
| 0.1483        | 0.56  | 1600 | 0.3114          | 0.9066   |
| 0.1266        | 0.59  | 1700 | 0.3893          | 0.8894   |
| 0.1131        | 0.63  | 1800 | 0.2696          | 0.9267   |
| 0.4377        | 0.66  | 1900 | 0.2953          | 0.9224   |
| 0.1578        | 0.7   | 2000 | 0.3059          | 0.9109   |
| 0.1273        | 0.73  | 2100 | 0.2474          | 0.9267   |
| 0.077         | 0.77  | 2200 | 0.2231          | 0.9382   |
| 0.0855        | 0.8   | 2300 | 0.2795          | 0.9368   |
| 0.0756        | 0.84  | 2400 | 0.2858          | 0.9210   |
| 0.2635        | 0.87  | 2500 | 0.2563          | 0.9353   |
| 0.1622        | 0.91  | 2600 | 0.2727          | 0.9325   |
| 0.1941        | 0.94  | 2700 | 0.2450          | 0.9239   |
| 0.0144        | 0.98  | 2800 | 0.2113          | 0.9454   |
| 0.0617        | 1.01  | 2900 | 0.1612          | 0.9454   |
| 0.0188        | 1.04  | 3000 | 0.2029          | 0.9425   |
| 0.0731        | 1.08  | 3100 | 0.1762          | 0.9612   |
| 0.0846        | 1.11  | 3200 | 0.1612          | 0.9569   |
| 0.0586        | 1.15  | 3300 | 0.2737          | 0.9353   |
| 0.0258        | 1.18  | 3400 | 0.1310          | 0.9670   |
| 0.0665        | 1.22  | 3500 | 0.1515          | 0.9540   |
| 0.0143        | 1.25  | 3600 | 0.2254          | 0.9440   |
| 0.0842        | 1.29  | 3700 | 0.2393          | 0.9468   |
| 0.0019        | 1.32  | 3800 | 0.1660          | 0.9526   |
| 0.013         | 1.36  | 3900 | 0.1413          | 0.9684   |
| 0.0177        | 1.39  | 4000 | 0.1455          | 0.9641   |
| 0.0128        | 1.43  | 4100 | 0.1291          | 0.9641   |
| 0.0222        | 1.46  | 4200 | 0.1567          | 0.9526   |
| 0.0017        | 1.5   | 4300 | 0.1640          | 0.9569   |
| 0.0009        | 1.53  | 4400 | 0.1861          | 0.9612   |
| 0.0007        | 1.57  | 4500 | 0.1440          | 0.9713   |
| 0.0026        | 1.6   | 4600 | 0.0940          | 0.9784   |
| 0.0006        | 1.64  | 4700 | 0.1282          | 0.9655   |
| 0.0023        | 1.67  | 4800 | 0.1341          | 0.9698   |
| 0.0002        | 1.71  | 4900 | 0.1099          | 0.9727   |
| 0.0013        | 1.74  | 5000 | 0.0872          | 0.9756   |
| 0.0001        | 1.78  | 5100 | 0.0908          | 0.9784   |
| 0.0006        | 1.81  | 5200 | 0.1034          | 0.9727   |
| 0.0009        | 1.85  | 5300 | 0.0940          | 0.9727   |
| 0.0           | 1.88  | 5400 | 0.1236          | 0.9655   |
| 0.0003        | 1.92  | 5500 | 0.1180          | 0.9684   |
| 0.0001        | 1.95  | 5600 | 0.1091          | 0.9698   |
| 0.0001        | 1.99  | 5700 | 0.1097          | 0.9698   |


### Framework versions

- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2